Downloads · 30 days
7
14% of all-time downloads
KoModernBERT-large-mlm-v19
CocoRoF/KoModernBERT-large-mlm-v19
KoModernBERT-large-mlm-v19 is a fill-mask model from CocoRoF. Use it when you need the model to fill a missing word. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
50
Public
Parameters
396M
28.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt2.4 GB · 60%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- License
- apache-2.0
- Model type
- modernbert
- Access
- Public
- Created
- Mar 24, 2025
- Updated
- Mar 24, 2025
- SHA
- a401052c
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
KoModernBERT-large-mlm-v19
This model is a fine-tuned version of CocoRoF/KoModernBERT-large-mlm-v18 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: nan
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 4
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 32
- total_train_batch_size: 1024
- total_eval_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.98) and epsilon=1e-07 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 75.7812 | 0.1156 | 500 | nan |
| 76.0172 | 0.2312 | 1000 | nan |
| 73.3032 | 0.3468 | 1500 | nan |
| 73.9782 | 0.4624 | 2000 | nan |
| 72.5503 | 0.5779 | 2500 | nan |
| 69.7412 | 0.6935 | 3000 | nan |
| 69.1634 | 0.8091 | 3500 | nan |
| 67.362 | 0.9247 | 4000 | nan |
Framework versions
- Transformers 4.49.0
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.1
- Task
- Fill-Mask
- Library
- transformers
- Type
- modernbert
- License
- apache-2.0
- Created
- Mar 24, 2025
- Updated
- Mar 24, 2025